© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 98496
    Prev
    Next
    INDEX
    Explanations

    obligatory, obligation, compelled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    il
    0.57
    au
    0.48
    af
    0.48
    ä
    0.46
    és
    0.46
    ai
    0.44
    al
    0.44
    ag
    0.44
    ab
    0.42
    ával
    0.41
    POSITIVE LOGITS
     obligatory
    0.58
     obligation
    0.53
     oblig
    0.52
     obliga
    0.51
     obligación
    0.50
     povinn
    0.50
     manda
    0.48
     Mandatory
    0.48
     обяза
    0.47
     mandates
    0.47
    Activations Density 0.012%

    No Known Activations